Sankalp Jain is a postdoctoral research fellow in the Early Translation Branch within the Division of Preclinical Innovation. As a member of the Adenine Team, Jain serves as a computational chemist, specializing in chemoinformatics, machine learning and molecular modeling. He applies and develops artificial intelligence-based machine learning prediction and classification models and performs virtual screening for various therapeutic endpoints. Additionally, he provides structure-based modeling project support (computational) for the Adenine Team.
Before joining NCATS, Jain worked as a research scientist at the Institute of Structural Biology, Helmholtz Zentrum in Munich, Germany, where he applied his computer-aided drug design expertise to multiple projects involving structure-based and ligand-based research. He also established an infrastructure of computational tools and methods for drug discovery, creating new virtual screening pipelines and results-evaluation methods.
Jain graduated with a master’s degree in life science informatics from the University of Bonn, North Rhine-Westphalia, Germany, in 2013. He then pursued his interest in the field of computational drug design and received a doctorate from the University of Vienna, Austria, in 2018. His Ph.D. focused on structure-based drug design studies on three major ABC transporters—BSEP, BCRP and P-glycoprotein—that helped in identifying the molecular features responsible for the inhibitory activity of ligands at these transporters. During his stay in Vienna, Jain also was involved in the European Union project EU ToxRisk and developed machine-learning models for predicting different toxicological outcomes and off-target effects related to, but not limited to, transporter proteins. Additionally, he contributed to developments in chemoinformatics and knowledge discovery while working across various organizations, including Fraunhofer IAIS (Germany), eADMET GmbH (Germany) and the European Bioinformatics Institute (United Kingdom).
Jain’s research interests are focused on cheminformatics and ligand- and structure-based drug design. He is interested specifically in the application and development of artificial intelligence, machine-learning-based methods to predict bioactivity for small molecules, and virtual screening approaches to accelerate the drug-development process.